© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8625
    Prev
    Next
    INDEX
    Explanations

    terms related to graphics and graphic design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "graphic" or "graphics"

    np_acts-logits-general · gemini-2.0-flash

    graphic or graphical design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abingdon
    -0.34
    kien
    -0.33
     disregard
    -0.30
    ท
    -0.28
     Abraham
    -0.28
     Allie
    -0.28
    Read
    -0.28
    掘
    -0.28
     esplor
    -0.28
    yya
    -0.27
    POSITIVE LOGITS
     propOrder
    0.82
     Италијани
    0.78
    expandindo
    0.77
    parsedMessage
    0.77
    OGND
    0.71
    TagMode
    0.71
    WithIOException
    0.70
    новништво
    0.70
    MemoryWarning
    0.68
     يتيمه
    0.68
    Activations Density 0.204%

    No Known Activations